Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
Eichenberger C, Neun M, Martin H, Herruzo P, Spanring M, Lu Y, Choi S, Konyakhin V, Lukashina N, Shpilman A, Wiedemann N, et al. (2022)
In: Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track. Kiela D, Ciccone M, Caputo B (Eds); Proceedings of Machine Learning Research, 176. PMLR: 97-112.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Eichenberger, Christian;
Neun, Moritz;
Martin, Henry;
Herruzo, Pedro;
Spanring, Markus;
Lu, Yichao;
Choi, Sungbin;
Konyakhin, Vsevolod;
Lukashina, Nina;
Shpilman, Aleksei;
Wiedemann, Nina;
Raubal, Martin
Alle
Alle
Herausgeber*in
Kiela, Douwe;
Ciccone, Marco;
Caputo, Barbara
Einrichtung
Abstract / Bemerkung
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over $10^{12}$ GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input.
Erscheinungsjahr
2022
Titel des Konferenzbandes
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track
Serien- oder Zeitschriftentitel
Proceedings of Machine Learning Research
Band
176
Seite(n)
97-112
Konferenz
NeurIPS 2021
Page URI
https://pub.uni-bielefeld.de/record/2982065
Zitieren
Eichenberger C, Neun M, Martin H, et al. Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes. In: Kiela D, Ciccone M, Caputo B, eds. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track. Proceedings of Machine Learning Research. Vol 176. PMLR; 2022: 97-112.
Eichenberger, C., Neun, M., Martin, H., Herruzo, P., Spanring, M., Lu, Y., Choi, S., et al. (2022). Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes. In D. Kiela, M. Ciccone, & B. Caputo (Eds.), Proceedings of Machine Learning Research: Vol. 176. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track (pp. 97-112). PMLR.
Eichenberger, Christian, Neun, Moritz, Martin, Henry, Herruzo, Pedro, Spanring, Markus, Lu, Yichao, Choi, Sungbin, et al. 2022. “Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes”. In Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, ed. Douwe Kiela, Marco Ciccone, and Barbara Caputo, 176:97-112. Proceedings of Machine Learning Research. PMLR.
Eichenberger, C., Neun, M., Martin, H., Herruzo, P., Spanring, M., Lu, Y., Choi, S., Konyakhin, V., Lukashina, N., Shpilman, A., et al. (2022). “Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes” in Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, Kiela, D., Ciccone, M., and Caputo, B. eds. Proceedings of Machine Learning Research, vol. 176, (PMLR), 97-112.
Eichenberger, C., et al., 2022. Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes. In D. Kiela, M. Ciccone, & B. Caputo, eds. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track. Proceedings of Machine Learning Research. no.176 PMLR, pp. 97-112.
C. Eichenberger, et al., “Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes”, Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, D. Kiela, M. Ciccone, and B. Caputo, eds., Proceedings of Machine Learning Research, vol. 176, PMLR, 2022, pp.97-112.
Eichenberger, C., Neun, M., Martin, H., Herruzo, P., Spanring, M., Lu, Y., Choi, S., Konyakhin, V., Lukashina, N., Shpilman, A., Wiedemann, N., Raubal, M., Wang, B., Vu, H.L., Mohajerpoor, R., Cai, C., Kim, I., Hermes, L., Melnik, A., Velioglu, R., Vieth, M., Schilling, M., Bojesomo, A., Marzouqi, H.A., Liatsis, P., Santokhi, J., Hillier, D., Yang, Y., Sarwar, J., Jordan, A., Hewage, E., Jonietz, D., Tang, F., Gruca, A., Kopp, M., Kreil, D., Hochreiter, S.: Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes. In: Kiela, D., Ciccone, M., and Caputo, B. (eds.) Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track. Proceedings of Machine Learning Research. 176, p. 97-112. PMLR (2022).
Eichenberger, Christian, Neun, Moritz, Martin, Henry, Herruzo, Pedro, Spanring, Markus, Lu, Yichao, Choi, Sungbin, Konyakhin, Vsevolod, Lukashina, Nina, Shpilman, Aleksei, Wiedemann, Nina, Raubal, Martin, Wang, Bo, Vu, Hai L., Mohajerpoor, Reza, Cai, Chen, Kim, Inhi, Hermes, Luca, Melnik, Andrew, Velioglu, Riza, Vieth, Markus, Schilling, Malte, Bojesomo, Alabi, Marzouqi, Hasan Al, Liatsis, Panos, Santokhi, Jay, Hillier, Dylan, Yang, Yiming, Sarwar, Joned, Jordan, Anna, Hewage, Emil, Jonietz, David, Tang, Fei, Gruca, Aleksandra, Kopp, Michael, Kreil, David, and Hochreiter, Sepp. “Traffic4cast at NeurIPS 2021 - Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes”. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track. Ed. Douwe Kiela, Marco Ciccone, and Barbara Caputo. PMLR, 2022.Vol. 176. Proceedings of Machine Learning Research. 97-112.
Google Scholar